Improvement of depiction of the intracranial arteries on brain CT angiography using deep learning reconstruction

To evaluate the ability of a commercialized deep learning recon-struction technique to depict intracranial vessels on the brain com-puted tomography angiography and compare the image quality with filtered-back-projection and hybrid iterative reconstruction in terms of objective and subjective measures. Forty-three patients under-went brain computed tomography angiography, and images were re-constructed using three algorithms: filtered-back-projection, hybrid iterative reconstruction, and deep learning reconstruction. The im-age noise, computed tomography attenuation value, signal-to-noise ratio, and contrast-to-noise ratio were measured in the bilateral cav-ernous segment of the internal carotid artery, vertebral artery, basi-lar apex, horizontal segment of the middle cerebral artery and used for the objective assessment of the image quality among the three different reconstructions. The subjective image quality score was significantly higher for the deep learning reconstruction than hybrid iterative reconstruction and filtered-back-projection images. The deep learning reconstruction markedly improved the reduction of blooming artifacts in surgical clips and coiled aneurysms. The deep learning reconstruction method generally improves the image qual-ity of brain computed tomography angiography in terms of objec-tive measurement and subjective grading compared with filtered-back-projection and hybrid iterative reconstruction. Especially, deep learning reconstruction is deemed advantageous for better depiction of small vessels compared to filtered-back projection and hybrid iter-ative reconstruction.